Multi-Target Backdoor Attacks Against Speaker Recognition
In this work, we propose a multi-target backdoor attack against speaker identification using position-independent clicking sounds as triggers. Unlike previous single-target approaches, our method targets up to 50 speakers simultaneously, achieving success rates of up to 95.04%. To simulate more realistic attack conditions, we vary the signal-to-noise ratio between speech and trigger, demonstrating a trade-off between stealth and effectiveness. We further extend the attack to the speaker verification task by selecting the most similar training speaker - based on cosine similarity - as a proxy target. The attack is most effective when target and enrolled speaker pairs are highly similar, reaching success rates of up to 90% in such cases.
Code (0)
등록된 구현이 없습니다.
Tasks
Speaker IdentificationSpeaker VerificationSpeaker RecognitionSimilar Papers 제목 키워드 기반
MASTERKEY: Practical Backdoor Attack Against Speaker Verification Systems
Speaker Verification (SV) is widely deployed in mobile systems to authenticate legitimate users by using their voice traits. In this work, we propose a backdoor attack MASTERKEY, to compromise the SV models. Different fr…
Backdoor AttackSpeaker VerificationBackdoor Attack against Speaker Verification
Speaker verification has been widely and successfully adopted in many mission-critical areas for user identification. The training of speaker verification requires a large amount of data, therefore users usually need to …
Backdoor AttackClusteringSpeaker VerificationUser IdentificationCUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks
Backdoor attacks have emerged as a critical security threat against deep neural networks in recent years. The majority of existing backdoor attacks focus on targeted backdoor attacks, where trigger is strongly associated…
Backdoor Attackbackdoor defenseOne-to-N & N-to-One: Two Advanced Backdoor Attacks Against Deep Learning Models
—In recent years, deep learning models have been widely deployed in various application scenarios. The training processes of deep neural network (DNN) models are time-consuming, and require massive training data and lar…
Face RecognitionBAAAN: Backdoor Attacks Against Autoencoder and GAN-Based Machine Learning Models
The tremendous progress of autoencoders and generative adversarial networks (GANs) has led to their application to multiple critical tasks, such as fraud detection and sanitized data generation. This increasing adoption …
Backdoor AttackBIG-bench Machine LearningFraud Detection